mlsanityData to 7 Oct 2026

Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning

arXiv 2105.14241 ↗First posted 29 May 2021cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

In news articles the lead bias is a common phenomenon that usually dominates the learning signals for neural extractive summarizers, severely limiting their performance on data with different or even no bias. In this paper, we introduce a novel technique to demote lead bias and make the summarizer focus more on the content semantics. Experiments on two news corpora with different degrees of lead bias show that our method can effectively demote the model's learned lead bias and improve its generality on out-of-distribution data, with little to no performance loss on in-distribution data.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 20 of its 23 references that are in the map. First posted on arXiv 29 May 2021.

Builds on

20 of 23 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  3. 2015Teaching Machines to Read and Comprehendcited by 1,039
  4. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
  5. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 279
  6. 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 245
  7. 2016Neural Summarization by Extracting Sentences and Wordscited by 114
  8. 2018Content Selection in Deep Learning Models of Summarizationcited by 64
  9. 2019Extractive Summarization of Long Documents by Combining Global and Local Contextcited by 59
  10. 2020Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensemblescited by 43
  11. 2019Searching for Effective Neural Extractive Summarization: What Works and What's Nextcited by 38
  12. 2019Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarizationcited by 28
8 more
  1. 2019Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Lossescited by 22
  2. 2020Improving Context Modeling in Neural Topic Segmentationcited by 21
  3. 2020Systematically Exploring Redundancy Reduction in Summarizing Long Documentscited by 21
  4. 2019A Closer Look at Data Bias in Neural Extractive Summarization Modelscited by 18
  5. 2018A Span Selection Model for Semantic Role Labelingcited by 15
  6. 2019Exploring Domain Shift in Extractive Text Summarizationcited by 15
  7. 2019Topics to Avoid: Demoting Latent Confounds in Text Classificationcited by 14
  8. 2020Do We Really Need That Many Parameters In Transformer For Extractive Summarization? Discourse Can Help !cited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 2; 2024: 3; 2025: 0; 2026: 1.

10 papers.

  1. 2022Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metricscited by 37
  2. 2024Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Biascited by 28
  3. 2022Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrievalcited by 20
  4. 2023A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understandingcited by 18
  5. 2022Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Modelscited by 6
  6. 2024Understanding Position Bias Effects on Fairness in Social Multi-Document Summarizationcited by 4
  7. 2021Modeling Endorsement for Multi-Document Abstractive Summarizationcited by 2
  8. 2024Self-Supervised Position Debiasing for Large Language Modelscited by 1
  9. 2023Evaluating Robustness of Dialogue Summarization Models in the Presence of Naturally Occurring Variationscited by 0
  10. 2026What Matters to an LLM? Behavioral and Computational Evidences from Summarizationcited by 0